© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 120002
    Prev
    Next
    INDEX
    Explanations

    YouTube video links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ား
    0.38
    ﾁ
    0.36
     दिलाया
    0.35
    Derivative
    0.34
     acknowledgement
    0.34
    Youtube
    0.34
     ack
    0.33
     acknowledging
    0.33
    ხვ
    0.33
    ឺ
    0.33
    POSITIVE LOGITS
     ترب
    0.40
     Grass
    0.38
    íram
    0.36
     schönen
    0.35
     Mikey
    0.35
     ক্যারি
    0.34
     grass
    0.34
    beiter
    0.34
    abilità
    0.34
     Ibadan
    0.34
    Activations Density 0.001%

    No Known Activations